Letter to the Editor

Undiagnosed sleep apnoea syndrome in patients with acute myocardial infarction: Potential importance of the STOP-BANG screening tool for clinical practice

OSA conveys worse clinical outcomes in patients with coronary artery disease. The STOP-BANG score is a simple tool that evaluates the risk of OSA and can be added to the large number of clinical variables and scores that are obtained during the management of patients with myocardial infarction (MI). Currently, machine learning (ML) is able to select and integrate numerous variables to optimize prediction tasks.

Can the integration of STOP-BANG score with clinical data and scores through ML better identify patients who experienced an in-hospital cardiovascular event after acute MI?

This is a prospective observational cohort study of 124 patients with acute MI of whom the STOP-BANG score classified 34 as low (27.4%), 30 as intermediate (24.2%), and 60 as high (48.4%) OSA-risk patients who were followed during hospitalization. ML implemented feature selection and integration across 47 variables (including STOP-BANG score, Killip class, GRACE score, and left ventricular ejection fraction) to identify those patients who experienced an in-hospital cardiovascular event (ie, death, ventricular arrhythmias, atrial fibrillation, recurrent angina, reinfarction, stroke, worsening heart failure, or cardiogenic shock) after definitive MI treatment. Receiver operating characteristic curves were used to compare ML performance against STOP-BANG score, Killip class, GRACE score, and left ventricular ejection fraction, independently.

There were an increasing proportion of cardiovascular events across the low, intermediate, and high OSA risk groups (P = .005). ML selected 7 accessible variables (ie, Killip class, leukocytes, GRACE score, c reactive protein, oxygen saturation, STOP-BANG score, and N-terminal prohormone of B-type natriuretic peptide); their integration outperformed all comparators (area under the curve, 0.83 [95% CI, 0.74-0.90]; P < .01).

The integration of the STOP-BANG score into clinical evaluation (considering Killip class, GRACE score, and simple laboratory values) of subjects who were admitted for an acute MI because of ML can significantly optimize the identification of patients who will experience an in-hospital cardiovascular event.

Obstructive sleep apnoea (OSA) affects ∼9–24% of the general population, and 90% remain undiagnosed. Those patients with undiagnosed moderate-to-severe OSA may be associated with an increased risk of perioperative complications. Our objective was to evaluate the proportion of surgical patients with undiagnosed moderate-to-severe OSA.

After research ethics board approval, patients visiting preoperative clinics were recruited over 4 yr and screened with the STOP-BANG questionnaire. The 1085 patients, who consented, subsequently underwent polysomnography (PSG) (laboratory or portable) before operation. Chart review was conducted in this historical cohort to ascertain the clinical diagnosis of OSA by surgeons and anaesthetists, blinded to the PSG results. The PSG study-identified OSA patients were further classified based on severity using the apnoea–hypopnoea index (AHI) cut-offs.

Of 819 patients, 111 patients had pre-existing OSA and 58% (64/111) were not diagnosed by the surgeons and 15% (17/111) were not diagnosed by the anaesthetists. Among the 708 study patients, PSG showed that 233 (31%) had no OSA, 218 (31%) patients had mild OSA (AHI: 5–15); 148 (21%) had moderate OSA (AHI: 15–30), and 119 (17%) had severe OSA (AHI>30). Before operation, of the 267 patients with moderate-to-severe OSA, 92% (n=245) and 60% (n=159) were not diagnosed by the surgeons and the anaesthetists, respectively.

We found that anaesthetists and surgeons failed to identify a significant number of patients with pre-existing OSA and symptomatic undiagnosed OSA, before operation. This study may provide an impetus for more diligent case finding of OSA before operation.

Obstructive sleep apnea (OSA) is linked to significant morbidity and mortality. OSA has received more attention recently, but the literature on OSA is scant in patients with severe mental illness (SMI). This project was undertaken to improve clinician knowledge and screening of OSA in persons with SMI.

One hundred SMI patients attending a primary care clinic were screened for symptoms and risk factors associated with OSA. The Epworth Sleepiness Scale was used to assess daytime sleepiness, and the STOP-Bang score was used to classify those at high risk for OSA.

Sixty-nine percent of patients were found to be at high risk for OSA. Sixteen percent had a previously confirmed diagnosis of OSA. Most patients reported that OSA was never discussed with them, and 71% of those at high risk were willing to be referred for a sleep evaluation.

Patients with SMI are at high risk for OSA, and screening for OSA appears to be inadequate. This screening can be done easily, seems acceptable to patients and may prove very beneficial as OSA diagnosis and treatment can improve mental and physical health outcomes in SMI patients.